A Super-Resolution Approach for Image Resizing of Infant Fingerprints With Vision Transformers
Authors:
- João H. P. MachadoJMJoão H. P. Machado
- Barbara De O. KoopBKBarbara De O. Koop
- Marcelo FilipakMFMarcelo Filipak
- Marco A. C. BarbosaMBMarco A. C. Barbosa
- Jefferson T. OlivaJOJefferson T. Oliva
- Luiz Fernando Puttow SouthierLSLuiz Fernando Puttow Southier
- Dalcimar CasanovaDCDalcimar Casanova
- Marcelo TeixeiraMTMarcelo Teixeira
Open Access
- 15 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 67718-67728
Abstract
Digital biometrics is one of the most widespread and reliable means of recognizing human identity. Despite being well-established for adults, digital biometrics for newborns constitutes a considerable open challenge in the literature. The very small size of the fingers exposes subtle features that can neither be visually inspected nor computationally captured. This leads conventional biometric matchers, which generally rely on the distance between ridges, not to work as expected for newborns. To some extent, this problem can be mitigated by increasing the scanner’s resolution, which is an expensive strategy. Besides, the saturation limit for resolution is unknown beforehand. Another alternative is to resize images using interpolation, but this can introduce unexpected noises or highlight preexisting ones. This paper proposes an approach for image resizing based on Super-Resolution networks that train Vision Transformer (ViT) how to handle newborn fingerprints, avoiding the introduction of noises while keeping and improving important details for biometric recognition. For biometric identification and verification, results show an increase in the order of 10% for resized images in comparison with traditional resizing algorithms.Keywords
Funding Information
- Infant.ID Ltda, National Council for Scientific and TechnologicalDevelopment (305069/2023-3)
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (001)
- Funding Authority for Studies and Projects (FINEP), Araucária Foundation, and UniversidadeTecnológica Federal do Parana
This publication has 16 references indexed in Scilit:
- Analyzing Similarity and Quality of Neonate Fingerprint Images subject to a Super-Resolution Technique2024
- Activating More Pixels in Image Super-Resolution Transformer2023
- SwinIR: Image Restoration Using Swin Transformer2021
- A Dense Pyramid Convolution Network for Infant Fingerprint Super-Resolution and Enhancement2021
- Multimodal biometric recognition for toddlers and pre-school children2017
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Single image super-resolution from transformed self-exemplars2015
- Recognizing infants and toddlers using fingerprints: Increasing the vaccination coverage2014
- On Single Image Scale-Up Using Sparse-Representations2012
- Introduction to Biometrics2011